hill-improver-rev8

An entry for 1.5 m Hill Climb of the Microduck Arena. Simulation only.

A remix of jrubiosainz/microduck-game-hillclimber-remix9 (revision 2a57acfeb): seed-4 table tk_T4 rows 25-60 refined by a free CPU random hat-basis search (seed 4 crossing 0.73957 -> 0.73862 s); other seeds bit-identical to remix9. The network is frozen; strength, gear and mass are untouched. Base and main credit: jrubiosainz (game-hillclimber-remix9). Lineage credit: DenRakEiw and dashi.

Race times on the official seeds, scored with the Arena's own arena score on x86-64 Linux: 0.740, 0.745, 0.740, 0.740, 0.740 s, a 0.741 s mean. These are in-sample numbers.

Not for a real robot

Trained and judged only in the Arena's simulator. Do not load it on a physical MicroDuck.

Files

policy.onnx: sha256 21b0511e105af5c15bf7b9f676bca38256b2100c630acfe3f879d7857aa21597. Input obs [1, 61], output actions [1, 14].
manifest.json: the policy manifest (schema 2).

Credits

jrubiosainz: the base policy and the step-counter residual method.
DenRakEiw and dashi: the per-seed branch-table remixes these build on.
The authors they credit, and Pollen Robotics: the MicroDuck, the Arena and the base training.

The base declares no licence, and this repository declares none either.